• Bankert, R. L., and M. Hadjimichael, 2007: Data mining numerical model output for single-station cloud-ceiling forecast algorithms. Wea. Forecasting, 22 , 11231131.

    • Search Google Scholar
    • Export Citation
  • Bellman, R. E., 1961: Adaptive Control Processes. Princeton University Press, 273 pp.

  • Beyer, K., J. Goldstein, R. Ramakrishnan, and U. Shaft, 1999: When is “nearest neighbor” meaningful? Proc. Seventh Int. Conf. on Database Theory, Jerusalem, Israel, ACM SIGMOD, 217–235.

    • Search Google Scholar
    • Export Citation
  • Bishop, C. M., 1995: Neural Networks for Pattern Recognition. Oxford University Press, 482 pp.

  • Bishop, C. M., 2006: Pattern Recognition and Machine Learning. Springer, 738 pp.

  • Black, T. L., 1994: The new NMC mesoscale Eta model: Description and forecast examples. Wea. Forecasting, 9 , 265278.

  • Blanchard, D. O., and R. E. Lopez, 1985: Spatial patterns of convection in south Florida. Mon. Wea. Rev., 113 , 12821299.

  • Breiman, L., 2001: Random forests. Mach. Learn., 45 , 532.

  • Breiman, L., J. H. Friedman, R. A. Olshen, and C. J. Stone, 1998: Classification and Regression Trees. Chapman & Hall, 368 pp.

  • Combs, C. L., W. Blier, W. Strach, and M. DeMaria, 2004: Exploring the timing of fog formation and dissipation over San Francisco Bay area using satellite cloud composites. Preprints, 13th Conf. on Satellite Meteorology and Oceanography, Norfolk, VA, Amer. Meteor. Soc., P4.12. [Available online at http://ams.confex.com/ams/13SATMET/techprogram/paper_78778.htm].

    • Search Google Scholar
    • Export Citation
  • Connell, B. H., K. Gould, and J. F. W. Purdom, 2001: High-resolution GOES-8 visible and infrared cloud frequency composites over northern Florida during the summers 1996–1999. Wea. Forecasting, 16 , 713724.

    • Search Google Scholar
    • Export Citation
  • Duda, R. O., and P. E. Hart, 1973: Pattern Classification and Scene Analysis. Wiley, 482 pp.

  • Egan, J. P., 1975: Signal Detection Theory and ROC Analysis. Academic Press, 277 pp.

  • Enger, I., L. J. Reed, and J. E. MacMonegle, 1962: An evaluation of 2–7-hr aviation terminal forecasting techniques. Federal Aviation Agency Systems Research and Development Service Tech. Publ. 20, Travelers Research Center, Inc., 43 pp.

    • Search Google Scholar
    • Export Citation
  • Fukunaga, K., 1990: Introduction to Statistical Pattern Recognition. Academic Press, 592 pp.

  • Girodo, M., R. W. Mueller, and D. Heinemann, 2006: Influence of three-dimensional cloud effects on satellite derived solar irradiance estimation—First approaches to improve the Heliosat methods. Sol. Energy, 80 , 11451159.

    • Search Google Scholar
    • Export Citation
  • Gneiting, T., and R. Ranjan, 2008: Combining probability forecasts. Department of Statistics Tech. Rep. 543, University of Washington, 24 pp.

    • Search Google Scholar
    • Export Citation
  • Hall, T. J., D. L. Reinke, and T. H. Vonder Haar, 1998: Forecasting applications of high-resolution satellite cloud composite climatologies. Wea. Forecasting, 13 , 1623.

    • Search Google Scholar
    • Export Citation
  • Hall, T. J., R. N. Thessin, G. J. Bloy, and C. N. Mutchler, 2010: Analog sky condition forecasting based on a k-nn algorithm. Wea. Forecasting, 25 , 14631478.

    • Search Google Scholar
    • Export Citation
  • Hansen, B., 2007: A fuzzy logic-based analog forecasting system for ceiling and visibility. Wea. Forecasting, 22 , 13191330.

  • Harvey Jr., L. O., K. R. Hammond, C. M. Lusk, and E. F. Mross, 1992: The application of signal detection theory to weather forecasting behavior. Mon. Wea. Rev., 120 , 863883.

    • Search Google Scholar
    • Export Citation
  • Hu, M. J. C., and H. E. Root, 1964: An adaptive data processing system for weather forecasting. J. Appl. Meteor., 13 , 513523.

  • Jedlovec, G. J., S. L. Haines, and F. J. LaFontaine, 2008: Spatial and temporal varying thresholds for cloud detection in GOES imagery. IEEE Trans. Geosci. Remote Sens., 46 , 17051717.

    • Search Google Scholar
    • Export Citation
  • Johns, M. V., 1961: An empirical Bayes approach to nonparametric two-way classification. Studies in Item Analysis and Prediction, H. Soloman, Ed., Stanford University Press, 221–232.

    • Search Google Scholar
    • Export Citation
  • Kelly, F. P., 1988: Spatial and temporal short range total cloud cover estimation by metric analysis of composite imagery. Ph.D. dissertation, Dept. of Atmospheric Science, Colorado State University, 152 pp.

  • Mason, I., 1982: A model for assessment of weather forecasts. Aust. Meteor. Mag., 30 , 291303.

  • Mason, S. J., and N. E. Graham, 2002: Areas beneath the relative operating characteristic (ROC) and relative operating levels (ROL) curves: Statistical significance and interpretation. Quart. J. Roy. Meteor. Soc., 128 , 21452166.

    • Search Google Scholar
    • Export Citation
  • McGranaghan, M., T. Ortmeyer, D. Crudele, T. Key, J. Smith, and P. Barker, 2008: Renewable systems interconnection study: Advanced grid planning and operations. Sandia National Laboratory Rep. SAND2008-0944 P, 122 pp.

    • Search Google Scholar
    • Export Citation
  • Murphy, A. H., and M. Ehrendorfer, 1987: On the relationship between the accuracy and value of forecasts in the cost–loss ratio situation. Wea. Forecasting, 2 , 243251.

    • Search Google Scholar
    • Export Citation
  • Nabney, I. T., 2001: Netlab: Algorithms for Pattern Recognition. Springer, 438 pp.

  • Peterson, W. W., T. G. Birdsall, and W. C. Fox, 1954: The theory of signal detectability. Trans. IRE Prof. Group Inf. Theory., 4 , 171212.

    • Search Google Scholar
    • Export Citation
  • Quinlan, J. R., 1986: Induction of decision trees. Mach. Learn., 1 , 81106.

  • Reinke, D. L., J. M. Forsythe, J. A. Kankiewicz, K. R. Dean, C. L. Combs, and T. H. Vonder Haar, 2003: Development and applications of regional cloud products from the CHANCES global cloud database. Preprints, 12th Conf. on Satellite Meteorology and Oceanography, Long Beach, CA, Amer. Meteor. Soc., P1.2. [Available online at http://ams.confex.com/ams/annual2003/techprogram/paper_52805.htm].

    • Search Google Scholar
    • Export Citation
  • Sutton, C. D., 2005: Classification and regression trees, bagging, and boosting. Data Mining and Data Visualization, C. R. Rao, E. J. Wegman, and J. L. Solka, Eds., Handbook of Statistics, Vol. 24, Elsevier, 303–329.

    • Search Google Scholar
    • Export Citation
  • Swets, J. A., 1973: The relative operating characteristic in psychology. Science, 182 , 9901000.

  • Vislocky, R. L., and J. M. Fritsch, 1997: An automated, observation-based system for short-term prediction of ceiling and visibility. Wea. Forecasting, 12 , 3143.

    • Search Google Scholar
    • Export Citation
  • Witten, I. H., and E. Frank, 2005: Data Mining: Practical Machine Learning Tools and Techniques. Morgan Kaufmann, 560 pp.

  • Zhang, G., B. E. Patuwo, and M. Y. Hu, 1998: Forecasting with artificial neural networks. Int. J. Forecasting, 14 , 3562.

All Time Past Year Past 30 Days
Abstract Views 0 0 0
Full Text Views 0 0 0
PDF Downloads 0 0 0

Performance of Observation-Based Prediction Algorithms for Very Short-Range, Probabilistic Clear-Sky Condition Forecasting

View More View Less
  • 1 The Aerospace Corporation, Silver Spring, Maryland
Restricted access

Abstract

Very short-range sky condition forecasts are produced to support a variety of military, civil, and commercial activities. In this investigation, six advanced, observation (obs)-based prediction algorithms were developed and tested that generated probabilistic sky condition forecasts for 1-, 2-, 3-, 4-, and 5-h forecast intervals, for local and regional target types, in six geographic regions within the continental United States. Three of the methods were based on predictive learning algorithms including neural network, random forest, and regression tree. The other three methods were statistical techniques including a k–nearest neighbor algorithm, a classifier based on the Bayes decision rule, and a multialgorithm ensemble. The performances of these six algorithms were compared with forecasts from three benchmark methods: basic persistence, the climatological-expectancy-of-persistence, and satellite cloud climatology. The obs database for each forecast target was composed of a multiyear, half-hourly time series of atmospheric parameters that included cloud features extracted from weather satellite imagery and meteorological variables extracted or derived from data assimilation–based model analyses generated by NCEP’s Eta Data Assimilation System. The performances of the advanced prediction algorithms exceeded those of the benchmarks at all five forecast intervals for both target types in all regions, on the basis of a group of metrics that included receiver operating characteristic score, sharpness, accuracy, expected best cost, and reliability.

Corresponding author address: Timothy J. Hall, The Aerospace Corporation, 8455 Colesville Rd., Suite 820–SLVR, Silver Spring, MD 20910. Email: timothy.j.hall@aero.org

Abstract

Very short-range sky condition forecasts are produced to support a variety of military, civil, and commercial activities. In this investigation, six advanced, observation (obs)-based prediction algorithms were developed and tested that generated probabilistic sky condition forecasts for 1-, 2-, 3-, 4-, and 5-h forecast intervals, for local and regional target types, in six geographic regions within the continental United States. Three of the methods were based on predictive learning algorithms including neural network, random forest, and regression tree. The other three methods were statistical techniques including a k–nearest neighbor algorithm, a classifier based on the Bayes decision rule, and a multialgorithm ensemble. The performances of these six algorithms were compared with forecasts from three benchmark methods: basic persistence, the climatological-expectancy-of-persistence, and satellite cloud climatology. The obs database for each forecast target was composed of a multiyear, half-hourly time series of atmospheric parameters that included cloud features extracted from weather satellite imagery and meteorological variables extracted or derived from data assimilation–based model analyses generated by NCEP’s Eta Data Assimilation System. The performances of the advanced prediction algorithms exceeded those of the benchmarks at all five forecast intervals for both target types in all regions, on the basis of a group of metrics that included receiver operating characteristic score, sharpness, accuracy, expected best cost, and reliability.

Corresponding author address: Timothy J. Hall, The Aerospace Corporation, 8455 Colesville Rd., Suite 820–SLVR, Silver Spring, MD 20910. Email: timothy.j.hall@aero.org

Save